LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

30B Epsilon GGML by TheBloke

 »  All LLMs  »  TheBloke  »  30B Epsilon GGML   URL Share it on

  13   
  Adventure   Alpaca   Cot   Ggml   Hippogriff   Instruct   Llama   Manticore   Merge   Mix   Quantized   Region:us   Roleplay   Rp   Story   Supercot   Superhot   Uncensored   Vicuna   Wizardlm
Model Card on HF 🤗: https://huggingface.co/TheBloke/30B-Epsilon-GGML 

30B Epsilon GGML Benchmarks

LLME Score: 0.09608
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
30B Epsilon GGML (TheBloke/30B-Epsilon-GGML)
🌟 Advertise your project 🚀

30B Epsilon GGML Parameters and Internals

Model Type 
llama, alpaca, vicuna, uncensored, cot, chain of thought, story, adventure, roleplay, rp, merge, mix, instruct, wizardlm, superhot, supercot, manticore, hippogriff
Use Cases 
Areas:
Chat UIs, Text-based adventure games
Applications:
Storytelling, Roleplay games
Primary Use Cases:
Storytelling and roleplay scenarios
Additional Notes 
30B Epsilon is a result of merging multiple language models and LoRAs without censorship and follows instructions in Alpaca format.
Supported Languages 
primary (Unknown), other ()
Training Details 
Data Sources:
SuperCOT, SuperHOT, wizardlmuncensored, hippogriff, manticore, StoryV2
Methodology:
Use of LoRAs and model merges.
Context Length:
8192
Model Architecture:
Composite model with LoRAs.
LLM Name30B Epsilon GGML
Repository 🤗https://huggingface.co/TheBloke/30B-Epsilon-GGML 
Model Size30b
Required VRAM13.7 GB
Updated2025-10-13
MaintainerTheBloke
Model Typellama
Model Files  13.7 GB   17.3 GB   15.7 GB   14.1 GB   18.3 GB   20.3 GB   19.6 GB   18.4 GB   22.4 GB   24.4 GB   23.0 GB   22.4 GB   26.7 GB   34.6 GB
GGML QuantizationYes
Quantization Typeggml
Model ArchitectureAutoModel
Licenseother

Best Alternatives to 30B Epsilon GGML

Best Alternatives
Context / RAM
Downloads
Likes
...e Llama 30B Instruct 2048 GGML0K / 13.7 GB920
Mpt 30B Chat GGML0K / 16.9 GB1973
Mpt 30B Instruct GGML0K / 16.9 GB1343
Mpt 30B GGML0K / 16.9 GB1417
LLaMa 30B GGML0K / 13.6 GB1124
Medalpaca Lora 30B 8bit0K / 0.2 GB015
Yayi2 30B Llama GGUF0K / 12.9 GB21910
LLaMA 30B GGUF0K / 13.5 GB6655
...e Llama 30B Instruct 2048 GGUF0K / 13.5 GB5724
30B Epsilon GGUF0K / 13.5 GB5125
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/30B-Epsilon-GGML.

Rank the 30B Epsilon GGML Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 51545 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer